Thanks for sharing AK! This AI Safety Benchmark Proof of Concept is an exciting first step in our mission to make AI safer for everyone. Our work would not be possible without the combined efforts of everyone involved!

Be sure to check out this coverage from AI Business of the MLCommons AI Safety v0.5 proof-of-concept benchmark that we announced earlier in the week to make AI safer for everyone: aibusiness.com/responsible-ai…

Thanks, John Russell for this excellent writeup about the MLCommons AI Safety v0.5 benchmark we announced earlier this week!

If you want to learn more and contribute to our efforts to make AI safer for everyone, join our #AISafety working group: mlcommons.org/working-groups…

Congratulations to AI at Meta on the release of Llama 3 and Llama Guard 2! We’re thrilled that Llama Guard 2 supports and is planning on expanding the MLCommons AI Safety v0.5 Taxonomy of Hazards for safer LLMs. llama.meta.com/llama3/

#AI #Benchmarks

Earlier this week we announced the release of the MLCommons AI Safety working group’s v0.5 benchmark POC. Read as members of our #AISafety working group discuss the POC and the importance of benchmarking in an overall approach to AI Safety: spectrum.ieee.org/ai-safety-benc…

Great writeup by Hackster.io on the #MLPerf Tiny v1.2 benchmark results. This was a very diverse set of submissions, which only showcases the importance of these kinds of #benchmarks .

This week, Stanford HAI released a comprehensive AI index that covers a wide range of #AI trends from 2023.

These findings showcase a need for the work our #AI Safety working group is doing, including the v0.5 benchmark POC announced earlier this week: mlcommons.org/2024/04/mlc-ai…

The MLPerf Tiny v1.2 benchmark results are out! MLPerf Tiny measures inference perf on ultra-low-power systems in the smallest form factors. Today’s results include 90+ performance measurements, including 18 for power across 6 organizations. Learn more: mlcommons.org/2024/04/mlperf…

MLCommons Announces AI Safety v0.5 Proof of Concept
ow.ly/wTXb50RhsmV MLCommons #HPC #TCIwire

Great writeup by Elblog on the MLCommons AI Safety v0.5 proof-of-concept benchmark that was announced earlier today: elblog.pl/2024/04/16/rev…

#AI , #benchmarks #machinelearning #AI Safety

Thanks for sharing SiliconANGLE! We're excited to take this first step towards making AI safer for everyone!

Today we announced the release of an AI Safety v0.5 benchmark POC. Learn more about the importance of this work from MLCommons AI Safety WG members in this IEEE Spectrum article, and join us in helping make AI better for everyone: spectrum.ieee.org/ai-safety-benc…

#AI #benchmarks

We are excited to announce the release of an MLCommons AI Safety benchmark POC. Built through an inclusive decision-making and engineering process, the POC validates our approach to a v1.0 AI Safety benchmark suite. Learn more: mlcommons.org/2024/04/mlc-ai…

#AI , #benchmarks

This is an exceptionally comprehensive AI index by Stanford HAI! It's clear that the work our AI Safety working group is doing to define and build #AISafety benchmarks is more important than ever: mlcommons.org/2023/10/mlcomm…

Thanks Brave Software for having David Kanter on #TheBraveTechnologist ! Be sure to tune in to learn more about our commitment to building a standard approach to #AISafety

Thanks for sharing these #MLPerf Inference v4.0 results, HPE! We’re always excited to see how our benchmarks are pushing advancements in AI performance!

community.hpe.com/t5/servers-sys…

Don’t miss out!

Applications close Friday, April 12 for the 2024 MLCommons ML & Systems Rising Stars Program! Awardees will be invited to attend the Rising Stars workshop in the NVIDIA HQ on July 15-16!

mlcommons.org/2024/02/call-f…

We're so excited for this talk by MLCommons Croissant co-chair Elena Simperl on our mission to standardize how ML datasets are described to make them more easily discovered and used. Be sure to join her at King's Institute for Artificial Intelligence on April 23!